Tagged “Browser Automation”

24 tools

Clear

agent-browser
agent-browser.dev

Category

Development Tools

What it does

agent-browser is a command-line interface for headless browser automation, designed for AI agents. It uses a Rust CLI and a Node.js daemon that manages a Playwright browser, and outputs compact text snapshots with element references.
OpenClaw
clawd.bot

Category

AI Agents

What it does

OpenClaw is a personal AI assistant that runs locally on macOS, Windows and Linux. It can be reached through messaging apps such as WhatsApp, Telegram, Discord and Slack, browse the web, read and write files, run shell commands, and keep persistent memory of user preferences.
Strawberry
strawberrybrowser.com

Category

AI Agents

What it does

Strawberry is a self-driving browser that uses AI agents to browse, research and automate tasks across tabs. Users can choose preset AI companions for sales, recruiting, data extraction, email and competitor analysis, or create custom ones.
Agent TARS
agent-tars.com

Category

AI Agents

What it does

Agent TARS is an open-source multimodal AI agent that lets users control and automate web browsing through natural language commands. It can interact with page elements via the browser DOM and is set up locally with an npx command.
MCP-B
mcp-b.ai

Category

Development Tools

What it does

MCP-B (Model Context Protocol for the Browser) is a framework that embeds MCP servers in web pages so AI assistants can call a site's functionality directly. It uses existing browser sessions for authentication and is distributed as an npm package and a Chrome extension.
BrowserOS
browseros.com

Category

AI Agents

What it does

BrowserOS is an open-source web browser built as a Chromium fork that runs AI agents locally on the user's device for tasks such as form filling, scheduling and research. It is released under the AGPL-3.0 license and supports Ollama and existing Chrome extensions.
ScreenEnv
huggingface.co

Category

Development Tools

What it does

ScreenEnv is a Python library for creating isolated Ubuntu desktop environments inside Docker containers. It lets developers and researchers build and test GUI agents that control the mouse, keyboard, windows, files and terminal, through a Direct Sandbox API or an MCP server.
rtrvr.ai
rtrvr.ai

Category

Automation

What it does

rtrvr.ai is a web automation tool that uses AI to retrieve structured data, run research across multiple browser tabs, and automate browser tasks. It runs as a DOM-based browser agent in Chrome and supports workflows such as lead extraction and CRM integration.
Airtop
airtop.ai

Category

AI Agents

What it does

Airtop is a cloud browser automation platform for AI agents. It lets agents log in to websites, navigate pages and extract data through natural language commands or an SDK, with cloud-hosted browser sessions.
Vy
vercept.com

Category

Productivity

What it does

Vy is a computer interface for macOS that lets users control their computer through natural language commands. It can work across applications, automate repetitive workflows on a schedule, and fill in web forms using stored information.
Gobii
gobii.ai

Category

Automation

What it does

Gobii is an API-first platform for launching serverless AI browser agents that automate web tasks such as navigating dynamic sites and extracting data. It offers free, Startup and Enterprise pricing tiers.
Simular
simular.ai

Category

AI Agents

What it does

Simular is a platform for developing AI agents that operate computers and interfaces the way humans do, automating tasks such as browsing, document work and routine workflows. The agents are described as open source, and the company publishes benchmark results for browser, computer and smartphone use.
Notte
notte.cc

Category

AI Agents

What it does

Notte is a browser framework for developing and deploying AI agents. It provides a single API for web scraping, browser automation, CAPTCHA solving, and secure credential and file management for agents.
Fellou
fellou.ai

Category

AI Agents

What it does

Fellou is an agentic web browser that runs research and multi-step tasks from natural language commands, including the generation of AI-written reports from web data. It also offers drag-and-drop cross-platform workflow automation and features such as split view and separate profiles for work and personal use.
Ace
generalagents.com

Category

Automation

What it does

Ace is a computer autopilot that executes tasks on a desktop by mimicking mouse and keyboard interaction. It is in an early research preview, with accuracy and latency benchmarks published and an invitation to sign up for access.
Anchor Browser
anchorbrowser.io

Category

AI Agents

What it does

Anchor Browser is a cloud-hosted browser runtime that lets AI agents navigate websites, interact with them and extract information. It offers CDP and Playwright control, isolated authenticated sessions and a pay-as-you-go pricing model.
Skyvern
skyvern.com

Category

Automation

What it does

Skyvern is a platform for automating browser-based workflows using AI and computer vision, such as filling out forms, fetching invoices and submitting applications. It is available as open-source software on GitHub and as a cloud service billed per page.
ReasonerAgent
reasoner-agent.maitrix.org

Category

AI Agents

What it does

ReasonerAgent is an open-source agent that operates in a Chromium-based browser to carry out multi-step web research and answer queries, such as flight search, online shopping comparisons and news gathering. It uses a planner built on world-model simulation with pretrained LLMs such as GPT-4o.
Ask Steve
asksteve.to

Category

Productivity

What it does

Ask Steve is a browser extension for Chrome and Edge that adds AI tools to web pages and text selections, so users can work with AI without copying content into separate chat applications. It supports custom buttons, chatting with webpages and PDFs, and connections to external systems through APIs.
Browseragent
browseragent.dev

Category

Automation

What it does

Browseragent is a platform for building AI automation workflows in a web browser without writing code. It runs AI models locally in the browser through the open-source BrowserAI library and offers a drag-and-drop interface and a Chrome extension.
Browserbase
browserbase.com

Category

Development Tools

What it does

Browserbase is a cloud platform for running and managing headless browsers for AI agents and applications. It is compatible with Playwright, Puppeteer and Selenium, and offers session recordings, live view, proxies and captcha solving.
PySpur
pyspur.dev

Category

AI Agents

What it does

PySpur is an open-source platform for building and deploying AI agents with a drag-and-drop interface and integration into APIs. It offers per-step monitoring, mid-pipeline evaluation, JSON export for version control, and SDKs for TypeScript and Python.
Crawl4AI
github.com

Category

Development Tools

What it does

Crawl4AI is an open-source web crawler and scraper that produces LLM-friendly Markdown and structured data from web pages. It supports browser control, CSS-based extraction and LLM-driven structured extraction, and can be installed via pip or Docker.
Bytespace
bytespace.ai

Category

Automation

What it does

Bytespace is a platform for automating tasks across websites using AI web-agents that can be recorded, shared and deployed as API endpoints. It offers residential proxies, captcha solving and virtual browsers for web automation.